rca_graph_add_node

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=false and destructiveHint=false, indicating a write operation that is not destructive. The description adds that it adds a node, which is consistent. However, it does not disclose additional behaviors like duplication handling or validation of graph existence.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (two sentences plus an Args block) with no fluff. It front-loads the primary purpose and uses a standard Args/Returns format. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with a clear input schema and an output schema. The description mentions the return type briefly. However, it does not specify prerequisites (e.g., that the graph must already exist) or potential side effects, leaving some gaps for a complete understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides rich detail (types, constraints, defaults). The description lists the parameters without adding new meaning beyond the schema, which has 0% coverage for parameter descriptions. The description repeats fields from the schema but does not enhance understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (add a typed node) and lists the allowed node types (metric, incident, symptom, root_cause, intermediate). This distinguishes it from sibling tools like rca_graph_remove_node and rca_graph_add_edge.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for adding nodes to a graph but does not explicitly state when to use this tool versus alternatives (e.g., add_edge or remove_node). No when-not-to-use or prerequisite context is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.